about.subtitle
This section features materials dedicated to open-source architectures that are shaping the evolution of modern linguistics and programming. We view open language models not merely as technological tools, but as platforms for independent research, ethical discourse, and the decentralization of expertise. Here, you will find analyses of algorithmic transparency, breakdowns of model weights, and training documentation, allowing you to verify results and adapt solutions to specific tasks without being tethered to proprietary ecosystems.
Indian company Sarvam AI has open-sourced two large language models – 30B and 105B – with a focus on supporting the languages of India.
AI: Events
Technical context • Research
Allen AI has introduced OLMo Hybrid, an open language model that combines two architectures for more efficient processing of long texts.
Two key libraries for running AI models on everyday devices have joined forces with Hugging Face – and it could change the future of local AI.
AI: Events
Development
The Chinese company has open-sourced the HY-1.8B-2Bit model with 2-bit quantization – it weighs less than many mobile apps.
AI: Events
Development
Allen AI has introduced Olmix, an open-source framework for data mixing in the language model training process, including pre-training, instruction tuning, and alignment.
Chinese company MiniMax has released M2.5, a family of open-weight models whose performance is approaching that of Claude 3.5 Sonnet.
Want to dive deeper into the world
of neuro-creativity?
Be the first to learn about new books, articles, and AI experiments
on our Telegram channel!